Merge pull request #539 from maxulysse/dev_annotation

Improving annotation
nf-core · May 12, 2022 · 818e8e6 · 818e8e6
2 parents b76d09d + 42509e6
commit 818e8e6
Show file tree

Hide file tree

Showing 24 changed files with 339 additions and 333 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -47,6 +47,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#511](https://github.com/nf-core/sarek/pull/511) - Sync `TEMPLATE` with `tools` `2.3.2`
 - [#520](https://github.com/nf-core/sarek/pull/520) - Improve annotation subworkflows
 - [#537](https://github.com/nf-core/sarek/pull/537) - Update workflow figure
+- [#539](https://github.com/nf-core/sarek/pull/539) - Update `CITATIONS.md`
 
 ### Fixed
 
@@ -78,6 +79,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#485](https://github.com/nf-core/sarek/pull/485) - `--skip_qc`, `--skip_markduplicates` and `--skip_bqsr` is now `--skip_tools`
 - [#538](https://github.com/nf-core/sarek/pull/538) - `--sequencing_center` is now `--seq_center`
 - [#538](https://github.com/nf-core/sarek/pull/538) - `--markdup_java_options` has been removed
+- [#539](https://github.com/nf-core/sarek/pull/539) - `--annotate_tools` has been removed
+- [#539](https://github.com/nf-core/sarek/pull/539) - `--cadd_cache`, `--cadd_indels`, `--cadd_indels_tbi`, `--cadd_wg_snvs`, `--cadd_wg_snvs_tbi` have been removed
+- [#539](https://github.com/nf-core/sarek/pull/539) - `--genesplicer` has been removed
+- [#539](https://github.com/nf-core/sarek/pull/539) - `conf/genomes.config` and `params.genomes_base` have been removed
 
 ## [2.7.1](https://github.com/nf-core/sarek/releases/tag/2.7.1) - Pårtejekna
 

diff --git a/CITATIONS.md b/CITATIONS.md
@@ -71,8 +71,23 @@
   > Danecek P, Auton A, Abecasis G, et al.: The variant call format and VCFtools. Bioinformatics. 2011 Aug 1;27(15):2156-8. doi: 10.1093/bioinformatics/btr330. Epub 2011 Jun 7. PubMed PMID: 21653522; PubMed Central PMCID: PMC3137218.
 
 - [VEP](https://pubmed.ncbi.nlm.nih.gov/27268795/)
+
   > McLaren W, Gil L, Hunt SE, et al.: The Ensembl Variant Effect Predictor. Genome Biol. 2016 Jun 6;17(1):122. doi: 10.1186/s13059-016-0974-4. PubMed PMID: 27268795; PubMed Central PMCID: PMC4893825.
 
+- [dbNSFP](https://pubmed.ncbi.nlm.nih.gov/33261662/)
+
+  > Liu X, et al.: dbNSFP v4: a comprehensive database of transcript-specific functional predictions and annotations for human nonsynonymous and splice-site SNVs. Genome Med. 2020 Dec 2;12(1):103. doi: 10.1186/s13073-020-00803-9. PubMed PMID: 33261662; PubMed Central PMCID: PMC7709417.
+
+- [LOFTEE](https://pubmed.ncbi.nlm.nih.gov/32461654/)
+
+  > Karczewski KJ, et al.: The mutational constraint spectrum quantified from variation in 141,456 humans. Nature. 2020 May;581(7809):434-443. doi: 10.1038/s41586-020-2308-7. PubMed PMID: 32461654; PubMed Central PMCID: PMC7334197.
+
+- [SpliceAI](https://pubmed.ncbi.nlm.nih.gov/30661751/)
+
+  > Jaganathan K, et al.: Predicting Splicing from Primary Sequence with Deep Learning. Cell. 2019 Jan 24;176(3):535-548.e24. doi: 10.1016/j.cell.2018.12.015. PubMed PMID: 30661751.
+
+- [SpliceRegion](https://github.com/Ensembl/VEP_plugins/blob/release/106/SpliceRegion.pm)
+
 ## R packages
 
 - [R](https://www.R-project.org/)
@@ -88,6 +103,7 @@
   > Trevor L Davis (2018). optparse: Command Line Option Parser.
 
 - [RColorBrewer](https://CRAN.R-project.org/package=RColorBrewer)
+
   > Erich Neuwirth (2014). RColorBrewer: ColorBrewer Palettes.
 
 ## Software packaging/containerisation tools
@@ -107,4 +123,5 @@
 - [Docker](https://dl.acm.org/doi/10.5555/2600239.2600241)
 
 - [Singularity](https://pubmed.ncbi.nlm.nih.gov/28494014/)
+
   > Kurtzer GM, Sochat V, Bauer MW. Singularity: Scientific containers for mobility of compute. PLoS One. 2017 May 11;12(5):e0177459. doi: 10.1371/journal.pone.0177459. eCollection 2017. PubMed PMID: 28494014; PubMed Central PMCID: PMC5426675.
diff --git a/assets/email_template.html b/assets/email_template.html
@@ -4,8 +4,10 @@
     <meta http-equiv="X-UA-Compatible" content="IE=edge" />
     <meta name="viewport" content="width=device-width, initial-scale=1" />
 
-    <!-- prettier-ignore -->
-    <meta name="description" content="nf-core/sarek: An open-source analysis pipeline to detect germline or somatic variants from whole genome or targeted sequencing" />
+    <meta
+      name="description"
+      content="nf-core/sarek: An open-source analysis pipeline to detect germline or somatic variants from whole genome or targeted sequencing"
+    />
     <title>nf-core/sarek Pipeline Report</title>
   </head>
   <body>

diff --git a/conf/genomes.config b/conf/genomes.config
diff --git a/conf/igenomes.config b/conf/igenomes.config
@@ -28,7 +28,8 @@ params {
             known_indels_tbi      = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/{1000G_phase1,Mills_and_1000G_gold_standard}.indels.b37.vcf.idx"
             mappability           = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/Control-FREEC/out100m2_hg19.gem"
             snpeff_db             = 'GRCh37.75'
-            vep_cache_version     = '104'
+            snpeff_genome         = 'GRCh37'
+            vep_cache_version     = 104
             vep_genome            = 'GRCh37'
             vep_species           = 'homo_sapiens'
         }
@@ -51,7 +52,8 @@ params {
             known_indels_tbi      = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/{Mills_and_1000G_gold_standard.indels.hg38,beta/Homo_sapiens_assembly38.known_indels}.vcf.gz.tbi"
             mappability           = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/Control-FREEC/out100m2_hg38.gem"
             snpeff_db             = 'GRCh38.99'
-            vep_cache_version     = '104'
+            snpeff_genome         = 'GRCh38'
+            vep_cache_version     = 104
             vep_genome            = 'GRCh38'
             vep_species           = 'homo_sapiens'
         }
@@ -78,7 +80,8 @@ params {
             mappability           = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Control-FREEC/GRCm38_68_mm10.gem"
             readme                = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/README.txt"
             snpeff_db             = 'GRCm38.99'
-            vep_cache_version     = '102'
+            snpeff_genome         = 'GRCm38'
+            vep_cache_version     = 102
             vep_genome            = 'GRCm38'
             vep_species           = 'mus_musculus'
         }
@@ -101,7 +104,8 @@ params {
             bwa                   = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BWAIndex/version0.6.0/"
             fasta                 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa"
             snpeff_db             = 'WBcel235.99'
-            vep_cache_version     = '104'
+            snpeff_genome         = 'WBcel235'
+            vep_cache_version     = 104
             vep_genome            = 'WBcel235'
             vep_species           = 'caenorhabditis_elegans'
         }

diff --git a/conf/modules.config b/conf/modules.config
@@ -963,24 +963,32 @@ process{
     withName: 'VCFTOOLS_SUMMARY'{
         ext.args         = "--FILTER-summary"
     }
-}
 
 // ANNOTATE
-process {
 
     withName: 'ENSEMBLVEP' {
-        ext.args          = '--everything --filter_common --per_gene --total_length --offline'
-        container         = { "nfcore/vep:104.3.${params.genome}" }
+        ext.args          = [
+            '--everything --filter_common --per_gene --total_length --offline',
+            (params.vep_dbnsfp && params.dbnsfp)                                  ? '--plugin dbNSFP,dbNSFP.gz,rs_dbSNP,HGVSc_VEP,HGVSp_VEP,1000Gp3_EAS_AF,1000Gp3_AMR_AF,LRT_score,GERP++_RS,gnomAD_exomes_AF' : '',
+            (params.vep_loftee)                                                   ? '--plugin LoF,loftee_path:/opt/conda/envs/nf-core-vep-104.3/share/ensembl-vep-104.3-0'                                      : '',
+            (params.vep_spliceai && params.spliceai_snv && params.spliceai_indel) ? '--plugin SpliceAI,snv=spliceai_scores.raw.snv.hg38.vcf.gz,indel=spliceai_scores.raw.indel.hg38.vcf.gz'                     : '',
+            (params.vep_spliceregion)                                             ? '--plugin SpliceRegion'                                                                                                     : ''
+        ].join(' ').trim()
+        if (!params.vep_cache)    container = { params.vep_genome ? "nfcore/vep:104.3.${params.vep_genome}" : "nfcore/vep:104.3.${params.genome}" }
         publishDir       = [
             mode: params.publish_dir_mode,
             path: { "${params.outdir}/reports/EnsemblVEP/${meta.id}/${meta.variantcaller}" },
             pattern: "*html"
         ]
     }
 
+    withName: ".*:ANNOTATION_MERGE:ENSEMBLVEP" {
+        ext.prefix       = {"${meta.id}_snpEff"}
+    }
+
     withName: 'SNPEFF' {
         ext.args          = '-nodownload -canon -v'
-        container         = { "nfcore/snpeff:5.0.${params.genome}" }
+        if (!params.snpeff_cache) container = { params.snpeff_genome ? "nfcore/snpeff:5.0.${params.snpeff_genome}" : "nfcore/snpeff:5.0.${params.genome}" }
         publishDir       = [
             mode: params.publish_dir_mode,
             path: { "${params.outdir}/reports/SnpEff/${meta.id}/${meta.variantcaller}" },
@@ -989,56 +997,36 @@ process {
         ]
     }
 
-    withName: 'ANNOTATION_BGZIPTABIX' {
+    withName: "NFCORE_SAREK:SAREK:ANNOTATE:.*:TABIX_BGZIPTABIX" {
         publishDir       = [
                 mode: params.publish_dir_mode,
                 path: { "${params.outdir}/annotation/${meta.id}/${meta.variantcaller}" },
                 pattern: "*{gz,gz.tbi}"
         ]
     }
-}
 
-if (params.tools && (params.tools.contains('snpeff') || params.tools.contains('merge'))) {
-    process {
-        withName: 'NFCORE_SAREK:SAREK:ANNOTATE:ANNOTATION_SNPEFF:ANNOTATION_BGZIPTABIX' {
-            ext.prefix       = {"${meta.id}_snpEff.ann.vcf"}
-            publishDir       = [
-                mode: params.publish_dir_mode,
-                path: { "${params.outdir}/annotation/${meta.id}/${meta.variantcaller}" },
-                pattern: "*{gz,gz.tbi}",
-                saveAs: { params.tools.contains('snpeff') ? it : null }
-            ]
-        }
+    withName: 'NFCORE_SAREK:SAREK:ANNOTATE:ANNOTATION_SNPEFF:TABIX_BGZIPTABIX' {
+        ext.prefix       = {"${meta.id}_snpEff.ann.vcf"}
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/annotation/${meta.id}/${meta.variantcaller}" },
+            pattern: "*{gz,gz.tbi}",
+            saveAs: { params.tools.contains('snpeff') ? it : null }
+        ]
     }
-}
 
-if (params.tools && (params.tools.contains('vep'))) {
-    process {
-        withName: 'NFCORE_SAREK:SAREK:ANNOTATE:ANNOTATION_ENSEMBLVEP:ANNOTATION_BGZIPTABIX' {
-            ext.prefix       = {"${meta.id}_VEP.ann.vcf"}
-        }
+    withName: 'NFCORE_SAREK:SAREK:ANNOTATE:ANNOTATION_ENSEMBLVEP:TABIX_BGZIPTABIX' {
+        ext.prefix       = {"${meta.id}_VEP.ann.vcf"}
     }
-}
 
-if (params.tools && (params.tools.contains('merge'))) {
-    process {
-        withName: 'NFCORE_SAREK:SAREK:ANNOTATE:ANNOTATION_MERGE:ANNOTATION_BGZIPTABIX' {
-            ext.prefix       = {"${meta.id}_snpEff_VEP.ann.vcf"}
-        }
+    withName: 'NFCORE_SAREK:SAREK:ANNOTATE:ANNOTATION_MERGE:TABIX_BGZIPTABIX' {
+        ext.prefix       = {"${meta.id}_snpEff_VEP.ann.vcf"}
     }
-}
 
-process {
+    // MULTIQC
+
     withName:'MULTIQC' {
         errorStrategy = {task.exitStatus == 143 ? 'retry' : 'ignore'}
         ext.args = { params.multiqc_config ? "--config $multiqc_custom_config" : "" }
     }
 }
-
-// process {
-    // withName: CUSTOM_DUMPSOFTWAREVERSIONS {
-    //     publishDir = [
-    //         mode: params.publish_dir_mode,
-    //         path: { "${params.outdir}/pipeline_info" },
-    //         pattern: '*_versions.yml'
-// }